Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy

TL;DR

This paper introduces three software tools—Zennit, CoRelAy, and ViRelAy—that facilitate dataset-wide explainability analysis of deep neural networks, enhancing reproducibility and user interaction in XAI research.

Contribution

The paper presents a comprehensive software suite for dataset-wide XAI analysis, integrating attribution methods, analysis pipelines, and interactive visualization to advance reproducibility and usability.

Findings

Provides standardized, customizable attribution framework in PyTorch

Enables efficient dataset-wide explanation analysis

Offers interactive visualization for model explanations

Abstract

Deep Neural Networks (DNNs) are known to be strong predictors, but their prediction strategies can rarely be understood. With recent advances in Explainable Artificial Intelligence (XAI), approaches are available to explore the reasoning behind those complex models' predictions. Among post-hoc attribution methods, Layer-wise Relevance Propagation (LRP) shows high performance. For deeper quantitative analysis, manual approaches exist, but without the right tools they are unnecessarily labor intensive. In this software paper, we introduce three software packages targeted at scientists to explore model reasoning using attribution approaches and beyond: (1) Zennit - a highly customizable and intuitive attribution framework implementing LRP and related approaches in PyTorch, (2) CoRelAy - a framework to easily and quickly construct quantitative analysis pipelines for dataset-wide analyses of explanations, and (3) ViRelAy - a web-application to interactively explore data, attributions, and analysis results. With this, we provide a standardized implementation solution for XAI, to contribute towards more reproducibility in our field.